Recent improvements in convolutional neural network (CNN)-based single image super-resolution (SISR) methods rely heavily on fabricating network architectures, rather than finding a suitable training algorithm other than simply minimizing the regression loss. Adapting knowledge distillation (KD) can open a way for bringing further improvement for SISR, and it is also beneficial in terms of model efficiency. KD is a model compression method that improves the performance of Deep Neural Networks (DNNs) without using additional parameters for testing. It is getting the limelight recently for its competence at providing a better capacity-performance tradeoff. In this paper, we propose a novel feature distillation (FD) method which is suitable for SISR. We show the limitations of the existing FitNet-based FD method that it suffers in the SISR task, and propose to modify the existing FD algorithm to focus on local feature information. In addition, we propose a teacher-student-difference-based soft feature attention method that selectively focuses on specific pixel locations to extract feature information. We call our method local-selective feature distillation (LSFD) and verify that our method outperforms conventional FD methods in SISR problems.
翻译:以进化神经网络(CNN)为基础的单一图像超分辨率(SISR)方法的近期改进主要依赖网络结构结构,而不是寻找适当的培训算法,而不只是将回归损失降到最低而已。适应知识蒸馏(KD)可以为SISSR的进一步改进开辟一条途径,这在模型效率方面也是有益的。KD是一种模型压缩方法,它改进了深神经网络(DNN)的性能,而没有使用额外的测试参数。它最近由于它有能力提供更好的能力性能交换而获得了亮点。在本文中,我们提出了一个适合SISSR的新型特性蒸馏(FD)方法。我们展示了基于FitNet的FD方法在SISSR任务中存在的局限性,并提议修改现有的FD算法,以当地地物信息为重点。此外,我们提议了一种基于师范差异的软特征关注方法,有选择地侧重于特定的像素位置,以提取地物信息。我们称之为SIRF的本地选择性特征蒸馏方法(LSFDFD),并核实我们的传统方法。